@InProceedings{zhao-EtAl:2018:N18-21,
  author    = {Zhao, Jieyu  and  Wang, Tianlu  and  Yatskar, Mark  and  Ordonez, Vicente  and  Chang, Kai-Wei},
  title     = {Gender Bias in Coreference Resolution: Evaluation and Debiasing Methods},
  booktitle = {Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 2 (Short Papers)},
  month     = {June},
  year      = {2018},
  address   = {New Orleans, Louisiana},
  publisher = {Association for Computational Linguistics},
  pages     = {15--20},
  abstract  = {In this paper, we introduce a new benchmark for co-reference resolution focused on gender bias, WinoBias. Our corpus contains Winograd-schema style sentences with entities corresponding to people referred by their occupation (e.g. the nurse, the doctor, the carpenter). We demonstrate that a rule-based, a feature-rich, and a neural coreference system all link gendered pronouns to pro-stereotypical entities with higher accuracy than anti-stereotypical entities, by an average difference of 21.1 in F1 score. Finally, we demonstrate a data-augmentation approach that, in combination with existing word-embedding debiasing techniques, removes the bias demonstrated by these systems in WinoBias without significantly affecting their performance on existing datasets.},
  url       = {http://www.aclweb.org/anthology/N18-2003}
}